Team

Team

These examples validate reliability for team-level tool usage and delegation.

ExampleDescription
Team Reliability Evaluation for News SearchEvaluate tool-call reliability for a team that researches AI news.

Simple Team Memory Performance Evaluation

Benchmark memory growth across 5 async runs of a weather team with persistent memory and history in Postgres.

Team Reliability Evaluation for News Search

Check whether a news-research team makes the expected delegation and web search tool calls.